ML Engineer - Commodities Applied ML (Summer Internship - Master's)

About the role

BAM's Commodities Data Science team seeks a master's-level ML Engineering Intern for a hands-on 10-week program in New York. You will apply Python, SQL, statistics, and machine learning to alternative and market data, developing geospatial analytics, models, data products, and investment insights with global commodities teams.

Responsibilities

• Translate commodities investment-team needs into testable analytical questions and practical data solutions.
• Analyze market and alternative datasets to form evidence-based views on investment hypotheses.
• Develop, validate, improve, and backtest statistical and machine-learning models and signals.
• Build reliable data pipelines and datasets for analytical and investment use cases.
• Deploy and maintain data products using cloud-native architecture principles.
• Communicate insights through visualizations, dashboards, and concise written outputs for varied audiences.

Projects and Collaboration

• Apply geospatial analytics to satellite imagery, aerial imagery, meteorological, and hydrological data.
• Develop applications such as crop-yield forecasting and other spatial data science solutions.
• Collaborate with global commodities investment teams, senior team members, peers, and broader interns.
• Present findings, assumptions, and uncertainties clearly to technical and non-technical stakeholders.
• Work independently and collaboratively in a fast-paced, ambiguous environment.

Requirements

• Master's-level background with a strong foundation in statistics, machine learning, Python, and SQL.
• Write clear, reproducible Python and SQL that others can review, challenge, and extend.
• Demonstrate familiarity with Git and software development practices.
• Apply robust modeling and backtesting practices, including preventing leakage, look-ahead bias, and overfitting.
• Use LLMs and agents judiciously, verify outputs, and reason through problems independently.
• Communicate clearly, remain organized, and respond constructively to feedback.